Filters








137,382 Hits in 5.3 sec

Predicting First Impressions with Deep Learning [article]

Mel McCurrie, Fernando Beletti, Lucas Parzianello, Allen Westendorp, Samuel Anthony, Walter Scheirer
2017 arXiv   pre-print
For instance, with just a glance, our first impression of a face may lead us to believe that a person is smart, worthy of our trust, and perhaps even our admiration - regardless of the underlying truth  ...  In this paper, we introduce a new convolutional neural network-based regression framework that allows us to train predictive models of crowd behavior for social attribute assignment.  ...  Code, data and supplemental material for this paper can be found at: http://github.com/mel-2445/ Predicting-First-Impressions Fig. 1 : 1 Computational modeling of social attributes allows us to predict  ... 
arXiv:1610.08119v2 fatcat:ufoygcg5wfbopbfpicbwj4rbsu

Revisiting Piggyback Prototyping: Examining Benefits and Tradeoffs in Extending Existing Social Computing Systems [article]

Daniel A. Epstein, Fannie Liu, Andrés Monroy-Hernández, Dennis Wang
2022 arXiv   pre-print
In the first version, the number of flowers are correlated with the heart rate of the person receiving the meditation guidance.  ...  When designing and evaluating BabyBot, a chatbot for Twitch that learns from how others converse, Seering et al. had to anticipate what problematic phrases people might attempt to make the bot learn, and  ... 
arXiv:2208.05456v1 fatcat:vrt3zq4iafghhixkieifsiox74

Deep Personality Trait Recognition: A Survey

Xiaoming Zhao, Zhiwei Tang, Shiqing Zhang
2022 Frontiers in Psychology  
Next, we describe the details of state-of-the-art personality trait recognition methods with specific focus on hand-crafted and deep learning-based feature extraction.  ...  Motivated by the great success of deep learning methods in various tasks, a variety of deep neural networks have increasingly been employed to learn high-level feature representations for automatic personality  ...  Subramaniam et al. (2016) employed two end-to-end deep learning models for audio-visual first impression analysis.  ... 
doi:10.3389/fpsyg.2022.839619 pmid:35645923 pmcid:PMC9136483 fatcat:5eh2ohzjwff5jb4yjn6rzrw5ye

Design of an explainable machine learning challenge for video interviews

Hugo Jair Escalante, Isabelle Guyon, Sergio Escalera, Julio Jacques, Meysam Madadi, Xavier Baro, Stephane Ayache, Evelyne Viegas, Yagmur Gucluturk, Umut Guclu, Marcel A. J. van Gerven, Rob van Lier
2017 2017 International Joint Conference on Neural Networks (IJCNN)  
We design a new challenge on explainability of learning machines for first impressions analysis. We describe the setting, scenario, evaluation metrics and preliminary outcomes of the competition.  ...  We focus on a particular area of the "Looking at People" (LAP) thematic domain: first impressions and personality analysis.  ...  The first author was supported by Red Temática CONACyT en Tecnologías del Lenguaje.  ... 
doi:10.1109/ijcnn.2017.7966320 dblp:conf/ijcnn/EscalanteGEJMBA17 fatcat:72igl6enebcfxd753x5i2dkemu

Bi-modal First Impressions Recognition using Temporally Ordered Deep Audio and Stochastic Visual Features [article]

Arulkumar Subramaniam, Vismay Patel, Ashish Mishra, Prashanth Balasubramanian, Anurag Mittal
2016 arXiv   pre-print
We propose a novel approach for First Impressions Recognition in terms of the Big Five personality-traits from short videos.  ...  We train two bi-modal end-to-end deep neural network architectures using temporally ordered audio and novel stochastic visual features from few frames, without over-fitting.  ...  We propose two end-to-end trained deep learning models that use audio features and face images for recognizing first impressions.  ... 
arXiv:1610.10048v1 fatcat:n7voeg47qraq5oz43m64mqgawq

Guest Editorial: Apparent Personality Analysis

Sergio Escalera, Xavier Baro, Isabelle Guyon, Hugo Jair Escalante
2018 IEEE Transactions on Affective Computing  
Average fusion of per-trait predictions. ChaLearn's first impressions [2] [7] 3 rd Personality/ Big Five Multimodal features learned with a two stream deep residual neural network.  ...  Gucluturk et al. describe in "Multimodal First Impression Analysis with Deep Residual Networks" 3 the methodology that obtained the third place in the first impressions competition [7] .  ... 
doi:10.1109/taffc.2018.2864230 fatcat:jlju6ayhqbdbhkjxcutnorgude

Deep Neural Networks for YouTube Recommendations

Paul Covington, Jay Adams, Emre Sargin
2016 Proceedings of the 10th ACM Conference on Recommender Systems - RecSys '16  
In this paper, we describe the system at a high level and focus on the dramatic performance improvements brought by deep learning.  ...  The paper is split according to the classic two-stage information retrieval dichotomy: first, we detail a deep candidate generation model and then describe a separate deep ranking model.  ...  We first score these two impressions with our model.  ... 
doi:10.1145/2959100.2959190 dblp:conf/recsys/CovingtonAS16 fatcat:d4ku6kfrundsnbqqs6wdf2vpf4

Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs

Heysem Kaya, Furkan Gurpinar, Albert Ali Salah
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
These multiple modalities are fed into modality-specific regressors to predict apparent personality traits and a variable that predicts whether the subject will be invited to the interview.  ...  In this application, audio, face and scene features are first computed from an input video CV, using rich feature sets.  ...  In this paper, we use deep learning based classifiers to predict apparent personality ratings.  ... 
doi:10.1109/cvprw.2017.210 dblp:conf/cvpr/KayaGS17 fatcat:uzqmijlo2vfhvjmwvabgqnv3p4

Impression Allocation for Combating Fraud in E-commerce Via Deep Reinforcement Learning with Action Norm Penalty

Mengchen Zhao, Zhao Li, Bo An, Haifeng Lu, Yifan Yang, Chen Chu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
First, we learn a seller behavior model to predict the sellers' fraudulent behaviors from the real-world data provided by one of the largest e-commerce company in the world.  ...  Then, we formulate the platform's impression allocation problem as a continuous Markov Decision Process (MDP) with unbounded action space.  ...  Part of this work is done during the first author's internship at Alibaba. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2018/548 dblp:conf/ijcai/ZhaoLALYC18 fatcat:l5ajdugfofcrxbchamfsvxjehe

Reinforcement Mechanism Design for Fraudulent Behaviour in e-Commerce

Qingpeng Cai, Aris Filos-Ratsikas, Pingzhong Tang, Yiwei Zhang
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In particular, first we set up a deep-learning framework for predicting the sellers' rationality, based on real data from any allocation algorithm.  ...  the objectives of the designer, with deep reinforcement learning for optimizing the performance based on these incentives.  ...  deep reinforcement learning.  ... 
doi:10.1609/aaai.v32i1.11452 fatcat:jf6ydeou55b2nfuv2rolbjxeu4

Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction [article]

Hong Wen and Jing Zhang and Yuan Wang and Fuyu Lv and Wentian Bao and Quan Lin and Keping Yang
2020 arXiv   pre-print
Although existing methods, typically built on the user sequential behavior path "impression→click→purchase", is effective for dealing with SSB issue, they still struggle to address the DS issue due to  ...  According to the conditional probability rule defined on the graph, it employs multi-task learning to predict some decomposed sub-targets in parallel and compose them sequentially to formulate the final  ...  In a nutshell, the first three methods learn to predict p ct r and p cvr using samples on the path "impression→click" and "click→purchase", respectively, then multiply them together to derive the click-through  ... 
arXiv:1910.07099v2 fatcat:lsvdmszkxfemfjvhxgkf7tmukq

Deep CTR Prediction in Display Advertising [article]

Junxuan Chen, Baigui Sun, Hao Li, Hongtao Lu, Xian-Sheng Hua
2016 arXiv   pre-print
To solve this issue, in this paper, we introduce a novel deep neural network (DNN) based model that directly predicts the CTR of an image ad based on raw image pixels and other basic features in one step  ...  Empirical evaluations on a real world dataset with over 50 million records demonstrate the effectiveness and efficiency of this method.  ...  With such learning ability, deep learning can be used as a good feature extractor and applied into many other applications [21, 26] .  ... 
arXiv:1609.06018v1 fatcat:r6cbdjoflfhhjgnajymm3sw36q

Combining Deep Facial and Ambient Features for First Impression Estimation [chapter]

Furkan Gürpınar, Heysem Kaya, Albert Ali Salah
2016 Lecture Notes in Computer Science  
In this work, we propose an approach to predict the first impressions people will have for a given video depicting a face within a context.  ...  First impressions influence the behavior of people towards a newly encountered person or a human-like agent.  ...  In our proposed approach, we estimate emotional facial expressions, as well as cues from the context of the face to predict first impressions.  ... 
doi:10.1007/978-3-319-49409-8_30 fatcat:cdr3e6tfmfbf3kyk5gbqv3mxmi

Deeply Supervised Semantic Model for Click-Through Rate Prediction in Sponsored Search [article]

Jelena Gligorijevic, Djordje Gligorijevic, Ivan Stojkovic, Xiao Bai, Amit Goyal, Zoran Obradovic
2018 arXiv   pre-print
This architecture improves the best-performing baseline deep neural architectures by 2\% of AUC for CTR prediction and by statistically significant 0.5\% of NDCG for query-ad matching.  ...  Commercial search engines typically use machine learning models for both query-ad relevance matching and click-through-rate (CTR) prediction.  ...  In [31] , features of an impression (query text, ad text, ad landing page, campaign ID, keywords, etc.) are learned automatically from the impression, in a deep architecture, to predict click probability  ... 
arXiv:1803.10739v1 fatcat:orcxowqcvfcujb35gukgm66aj4

Visual Attention on the Sun: What Do Existing Models Actually Predict? [article]

Jia Li, Daowei Li, Kui Fu, Long Xu
2018 arXiv   pre-print
Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era.  ...  By benchmarking existing models on VASUN, we find the performances of many state-of-the-art deep models drop remarkably, while many classic shallow models perform impressively.  ...  Instead, many classic shallow models that are bio-inspired or non-deep learning-based still perform impressively on solar images and significantly outperform the deep models.  ... 
arXiv:1811.10004v1 fatcat:hk7aixazlrdyjdlt7sampwf3y4
« Previous Showing results 1 — 15 out of 137,382 results